CN105592301B - Picture pick-up device and its control method and supervision camera system - Google Patents

Picture pick-up device and its control method and supervision camera system Download PDF

Info

Publication number
CN105592301B
CN105592301B CN201510751841.0A CN201510751841A CN105592301B CN 105592301 B CN105592301 B CN 105592301B CN 201510751841 A CN201510751841 A CN 201510751841A CN 105592301 B CN105592301 B CN 105592301B
Authority
CN
China
Prior art keywords
subject
detection line
picture pick
detection
foot
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201510751841.0A
Other languages
Chinese (zh)
Other versions
CN105592301A (en
Inventor
诸藤刚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Canon Inc
Original Assignee
Canon Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Canon Inc filed Critical Canon Inc
Publication of CN105592301A publication Critical patent/CN105592301A/en
Application granted granted Critical
Publication of CN105592301B publication Critical patent/CN105592301B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/254—Analysis of motion involving subtraction of images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/42—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
    • G06V20/693—Acquisition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
    • G06V20/695—Preprocessing, e.g. image segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
    • G06V20/698—Matching; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/61—Control of cameras or camera modules based on recognised objects
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/66—Remote control of cameras or camera parts, e.g. by remote control devices
    • H04N23/661—Transmitting camera control signals through networks, e.g. control via the Internet
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/68—Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations
    • H04N23/681—Motion detection
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/698—Control of cameras or camera modules for achieving an enlarged field of view, e.g. panoramic image capture
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30232—Surveillance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/03—Recognition of patterns in medical or anatomical images
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/63—Control of cameras or camera modules by using electronic viewfinders
    • H04N23/633—Control of cameras or camera modules by using electronic viewfinders for displaying additional information relating to control or operation of the camera
    • H04N23/634—Warning indications

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Studio Devices (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Alarm Systems (AREA)

Abstract

The present invention provides a kind of picture pick-up device and its control method and supervision camera system.Picture pick-up device includes：Subject detection unit, for, via shooting image captured by comprehensive pick-up lens, detecting the region of subject from camera unit；Setting unit, for position corresponding with the direction perpendicular to horizontal plane to be arranged in the shooting image；Determining means determines the judgement position passed through for being used to judge the subject in the region of the subject for the relationship between the region based on the subject in set position and the shooting image；And passing through detection unit, the detection line for judging position and be arranged on the shooting image for being determined based on the determining means detects the subject relative to passing through for the detection line.

Description

Picture pick-up device and its control method and supervision camera system
Technical field
The present invention relates to picture pick-up device and its control methods and supervision camera system, more particularly, to pass through monitoring Detection object or the surveillance technology for obtaining details.
Background technique
Traditionally, the arrangement monitoring photograph at each of shop or parking lot or on the enclosure wall around specific building Machine, to monitor the third-party invasion of theft or illegal activities or monitoring from outside in shop or parking lot.
In supervision camera system, for automatic measurement and the activity for analyzing people in public places or in leisure facilities It efficiently taken precautions against natural calamities, monitored and the demand of the system of managed operation has increased.For example, according to indicate it is current how many The information that visitor is entering and leaving facility and they are being moved to which direction with speed how soon holds the part in facility Transportation load or facility use state.Congestion state around viewing area can also be predicted, and obtained to keeping away Exempt from the information of crowded direction guidance crowd.
Japanese Unexamined Patent Publication 8-123935 is described even if for example in the collecting and distributing pedestrian of entrance to uncertain direction The method that people etc. can be also counted based on direction and steadily in the case of movement.It also describes due to using wide-angle lens It is first-class and in the case where causing the peripheral portion of video to be distorted, use according to the curves of lens distortions as counting line, wherein The curve is becoming straight line when projection is on the ground into camera shooting real space for curve on picture.
Japanese Unexamined Patent Publication 6-223157, which is described through image procossing, is arranged virtual door on observation image, and is moving When the moving-wire or perspective view of kinetoplast move through virtual door, moving body is detected in the case where not interfering nature to flow.
However, in subject when by passing through near detection line, subject is according to shot in these traditional technologies The size (height) of body may intersect with by detection line, so as to cause error detection.
Relatively wide range can be shot using fish-eye comprehensive camera, thus can from top to bottom effectively Monitor wide space.However, cannot ignore when shooting the relatively narrow space in such as small shop using comprehensive camera The size of subject.In subject when by passing through near detection line, which may partly be handed over by detection line Fork, and error detection may occur.
The present invention has been made in view of the above problem, even and if the present invention provide and a kind of passing through detection in subject Line also reduces error detection in the case where nearby passing through and realizes the stable technology by detection.
Summary of the invention
According to an aspect of the present invention, a kind of picture pick-up device is provided, including：Subject detection unit is used for from camera shooting Unit detects the region of subject via shooting image captured by comprehensive pick-up lens；Setting unit, for being arranged State the position corresponding with the direction perpendicular to horizontal plane in shooting image；Determining means, for based on set position Relationship between the position in the region of the subject in the shooting image, is used in the region to determine the subject Judge the judgement position of the subject passed through；And by detection unit, for what is determined based on the determining means Set detection line on the judgement position and the shooting image, to detect whether the subject passes through the detection Line.
According to another aspect of the present invention, a kind of supervision camera system is provided, including：Above-mentioned picture pick-up device；And Information processing equipment, for obtaining image from the picture pick-up device via network.
According to another aspect of the invention, a kind of control method of picture pick-up device is provided, including：From camera unit via complete Image is shot captured by orientation pick-up lens to detect the region of subject；Be arranged it is described shooting image in perpendicular to water The corresponding position in the direction of plane；The position in the region based on the subject in set position and the shooting image Relationship between setting, in the region to determine the subject for judging the judgement position of the subject passed through；With And based on detection line set on the judgement position and the shooting image determined, whether to detect the subject Across the detection line.
By the explanation below with reference to attached drawing to exemplary embodiments, other feature of the invention be will be apparent.
Detailed description of the invention
Fig. 1 is the figure for showing the example of configuration of supervision camera system according to an embodiment of the present invention.
Fig. 2 is the figure for showing the example of omnidirectional images according to first embodiment.
Fig. 3 is the figure for showing the example of omnidirectional images according to first embodiment.
Fig. 4 is the figure for showing the example of omnidirectional images according to first embodiment.
Fig. 5 is the block diagram for showing the example of configuration of picture pick-up device according to first embodiment.
Fig. 6 is the flow chart for showing the process for the processing that picture pick-up device according to first embodiment executes.
Fig. 7 is the figure for showing the example of omnidirectional images according to the second embodiment.
Fig. 8 is the figure for showing the example of omnidirectional images according to the second embodiment.
Fig. 9 is the flow chart for showing the process for the processing that picture pick-up device according to the second embodiment executes.
Figure 10 is the block diagram for showing the example of configuration of picture pick-up device according to the second embodiment.
Figure 11 is the figure for showing the example of configuration of supervision camera system according to the third embodiment.
Specific embodiment
Carry out the exemplary embodiments that the present invention will be described in detail below with reference to attached drawing.It should be noted that described in these embodiments Relative configuration, numeral expression and the digital value of component do not limit the scope of the invention, unless otherwise stated.
In the present embodiment, comprehensive camera is set on omnidirectional images in vertical direction (on real space The direction of horizontal plane) on position as vertical reference position.Explanation is based on vertical reference position and body position shot Between positional relationship and detection of the setting for passing through line to subject is judged in body region shot judgement position, And the example by detection is carried out based on position is judged across detection line.
Reference Fig. 1 is illustrated to the example of the configuration of supervision camera system according to an embodiment of the present invention first.Monitoring is shone Camera 10 includes picture pick-up device 101 and client terminal 102.Picture pick-up device 101 is connected with client terminal 102 via network 103.
Picture pick-up device 101 and is installed in a manner of vertically downward for example including fish-eye comprehensive camera To ceiling.The video of subject 104 captured by picture pick-up device 101 is sent to client terminal 102 or note via network 103 Record server (not shown).The display equipment or be connected to record clothes that display equipment 105 is included in client terminal 102 The display equipment of business device (not shown), and show omnidirectional images 106 captured by picture pick-up device 101.
Fig. 2 is to show the inside that shop is shot being installed in a manner of vertically downward to the picture pick-up device 101 of ceiling And the example of the omnidirectional images 106 obtained.According to the instruction of operator's (not shown), detection line 203 is preset with for example Detect the number of pass times of people or passing through for warning people.If subject 104 is walked along channel, may be with detection line 203 Intersect, and picture pick-up device 101 may mistakenly judge to have passed through for people.
Vertical reference position 201 indicates the vertical direction relative to ground.It particularly, is in a manner of vertically downward Vertical reference position when shooting image to the picture pick-up device 101 of ceiling is installed.Due to the fish being arranged in picture pick-up device 101 The characteristic of glasses head, vertical reference position 201 are arranged at the center of shooting image.Note that user can be on display picture Specified vertical reference position.Vertical reference position relative to centered on shoots image with radial formation.By subject 104 The shortest distance position for being located relative to vertical reference position 201 (that is, upright position of picture pick-up device 101) part definition For the position of the foot 202 of subject 104.That is, the position of foot 202 is determined as to be used to judge that subject to pass through line Judgement position.Intersection (passing through) to foot 202 relative to set detection line 203 detects.Due to 202 He of foot Detection line 203 is present in same plane (ground), thus can reduce error detection and can carry out stable passing through detection.
For example, can detecte subject 104 when subject 104 as shown in Figure 3 is moved to the position of subject 104a Foot 202 pass through detection line 203 and be moved to the foot 301 of subject 104a.Therefore, to subject by carrying out Judgement appropriate.
On the other hand, Fig. 4 shows subject 104 and is moved to the position of subject 104b along channel (parallel with detection line 203) The case where setting.In this case, during the foot 401 for being moved to subject 104b, the foot 202 of subject 104 never with Detection line 203 is intersected.Accordingly it is possible to prevent error detection.
Reference Fig. 5 is then illustrated to the example of the configuration of picture pick-up device 101 according to first embodiment.Picture pick-up device 101 Including fish eye lens (comprehensive pick-up lens) 501, imaging sensor 502, video signal processing unit 503, distortion correction list Member 504, overlapped elements 505, encoder 506, network unit 507, control unit 508, moving body detection unit 509, setting are single Member 510 and pass through detection unit 511.When control unit 508 reads and executes computer program from memory (not shown), control Make the work of each constituent element.
The video of subject 104 is projected to imaging sensor 502 via fish eye lens 501.Projected image is converted into Electric signal, and send it to video signal processing unit 503.The progress of video signal processing unit 503 such as color separated, The processing of white balance and Gamma correction etc., and processing result is exported to distortion correction unit 504.In response to client terminal 102 request, distortion correction unit 504 360 ° of panoramas, 180 ° of scapes of enjoying a double blessing, 4 frames to the state with omnidirectional images or such as Distorted image corresponding with the various display patterns of 8 frames extraction etc. is extracted to be corrected and handle.It in the present embodiment, can be with It carries out appropriate passing through detection before the correction process of distorted image.
Overlapped elements 505 prepare the image layer for the detection line 203 being distorted in advance, and by 203 weight of detection line It is stacked on omnidirectional images 106.For unfolded image (360 ° of panoramas, 180 ° of scapes of enjoying a double blessing, 4 frames extract or 8 frames extract), overlapping is single First 505 overlapping times, date/time, camera title and azimuth etc. and export image.
Note that will the information overlaps such as time, date/time, camera title and azimuth in omnidirectional images In the case where on 106, character and anamorphose at expansion (distorted image correction).Therefore, by the information overlap in black image The information is directly removed when portion and in the client expansion (distorted image correction), this is effective.It is alternatively possible to should Information as data be embedded in black image portion, and in the client be unfolded when extract the information.
Then, encoder 506 carries out coded treatment and exports data to network unit 507.Network unit 507 will count According to via the distribution of network 103 to record server 500 or client terminal 102.
The control command sent from record server 500 or client terminal 102 is via network 103 by network unit 507 It receives, and is sent to control unit 508 and the explanation of controlled unit 508.For example, being sent from client terminal 102 To indicate to change to when the change order of 180 ° of scapes of enjoying a double blessing, control unit 508 explains the order, and distortion correction unit 504 carry out the change to 180 ° of scapes of enjoying a double blessing.
Moving body detection unit 509 is from (complete via shooting image captured by fish eye lens (comprehensive pick-up lens) 501 Bearing images 106) detection moving body (subject 104).Setting unit 510 is arranged in shooting image (omnidirectional images 106) Vertical reference position 201 corresponding with the upright position of fish eye lens (comprehensive pick-up lens) 501.Setting unit 510 is also The position of the foot 202 of moving body (subject 104) is arranged in position based on vertical reference position 201 and moving body (subject) It sets.
Pass through the inspection of position of the detection unit 511 based on foot 202 and setting in shooting image (omnidirectional images 106) Survey line 203, to moving body (subject 104) relative to detection line 203 by detecting.
Illustrate the mistake for the processing that picture pick-up device 101 according to first embodiment executes below with reference to the flow chart of Fig. 6 Journey.
In step s 601, control unit 508 will project to complete on imaging sensor 502 via fish eye lens 501 Bearing images 106 are sent to display equipment 105 to be displayed in full screen.In step S602, control unit 508 controls moving body Detection unit 509 is to detect moving body (subject 104) in omnidirectional images 106.Note that being executed logical in step S602 Cross the processing that such as background subtraction detects moving body from omnidirectional images 106.This is because since omnidirectional images have Distortion, thus affinity is higher than stencil matching.In step S603, control unit 508 controls setting unit 510 and is examined with being arranged The position of the foot of the moving body (subject 104) measured.
With reference to as described in Fig. 2~4, setting unit 510 is by the upright position of picture pick-up device 101 (for example, omnidirectional images 106 center) it is set as vertical reference position 201, and subject 104 and vertical reference position 201 is nearest Position is determined as the position of the foot 202 of subject 104.
In step s 604, control unit 508 is controlled through detection unit 511, to be based on default detection line 203 and be shot The foot 202 of body 104, judges whether subject 104 has passed through detection line 203.If subject 104 has passed through detection line 203, Then processing enters step S605.On the other hand, if subject 104 does not pass through detection line 203, processing returns to step S601。
In step S605, control unit 508 executes and detects subject 104 across the corresponding processing of detection line 203. For example, in order to alert passing through for the subject in supervision camera system, control unit 508 can will be passed through by testing result Client terminal 102 is sent to by network unit 507, with display equipment 105 on show alert or 102 side of client terminal into Row sound notification.If client terminal 102 is calculated through total number of persons, control unit 508 can will be related with by total number of persons Information be sent to client terminal 102 via network unit 507.Client terminal 102 can be counted to by number, or Counted out number is shown in display equipment 105.Various other processing corresponding with purpose can be executed.Shown in Fig. 6 Everywhere in reason this terminate.
Note that can be executed on client terminal 102 through a part of processing of detection processing etc. a series of or All.The present embodiment can also be applied to according to different fish-eye characteristics (for example, increasing imaging sensor 502 Imaging area and the comprehensive camera lens for improving periphery resolution ratio) and have adjusted the omnidirectional images of shape.In this case, For example, the present invention can be applied equally to not have positive round shape and have elliptical omnidirectional images.
As described above, in the present embodiment, the upright position of comprehensive camera is defined as base position, it is based on benchmark Positional relationship between position and body position shot and foot is set, and carried out based on foot relative to passing through for detection line Pass through detection.Therefore, even if in subject by passing through near detection line, error detection and real can also be reduced Show and stable has passed through detection.
In another embodiment, the example that will be described below：Foot to the position of centre of gravity of subject relative to subject Height detected, by the second detection line will be arranged in detected height reflection detection line on the ground, and And the intersection (passing through) to position of centre of gravity relative to the second detection line detects, and thus carries out passing through detection.
Fig. 7 show installed in a manner of vertically downward to ceiling picture pick-up device 101 shoot shop inside and The example of the omnidirectional images 106 of acquisition.Operator presets detection line 203 for example to detect through number or warning people Pass through.
As with the first embodiment, the upright position of picture pick-up device 101 (centers of omnidirectional images 106) are arranged For vertical reference position 201, and subject 104 is set by the part nearest with vertical reference position 201 of subject 104 Foot 802.It is assumed that the position of centre of gravity 701 to subject 104 is detected relative to passing through for detection line 203.In the situation Under, if subject 104 is moved to the position of subject 104c, position of centre of gravity 701 be moved to position of centre of gravity 702 and with inspection Survey line 203 intersects.Therefore, mistakenly it is judged as that subject 104 passes through.
In order to prevent this situation, as shown in figure 8, height to position of centre of gravity 701 relative to the foot 802 of subject 104 Degree is configured.Detection line 203 on ground be moved to same vertical reference position be separated by it is corresponding with set height away from From position, and update the setting of detection line 801.Friendship to the position of centre of gravity 701 of subject 104 relative to detection line 801 Fork (passing through) is detected, to carry out passing through detection.
For example, being separated by the line of the position of connection vertical reference position 201 and foot 802, with the position of foot 802 pre- The position of centre of gravity 701 of subject 104 is set at the position of set a distance.It can be according to from vertical reference position 201 to foot 802 The distance of position, come the preset distance being arranged between the position of foot 802 and position of centre of gravity 701.For example, if subject 104 Nearby or near the circular edge of omnidirectional images 106, then preset distance is arranged short positioned at vertical reference position 201. This is because being viewed from above subject 104, and be shot if subject 104 is present near vertical reference position 201 The length (finding height) of body 104 is short.It is alternatively possible to estimate position of centre of gravity by analyzing detected subject 104 (for example, position near waist), and position of centre of gravity 701 can be set by estimated position.Furthermore it is possible to will be by It takes the photograph between the part farthest with vertical reference position 201 of the part and subject nearest with vertical reference position 201 of body Midpoint is set as the position of centre of gravity 701 of subject 104.
Since detection line 801 and position of centre of gravity 701 (position of centre of gravity 702) being arranged on same plane (sustained height), because And error detection can be reduced and can carry out stable passing through detection.
Illustrate the example of the configuration of the picture pick-up device 101 according to the present embodiment below with reference to Figure 10.Except reference Fig. 5 institute Other than the constituent element of explanation, configuration shown in Fig. 10 further includes detection line setting unit 1001.Detection line setting unit 1001 The detection line for having been carried out the corresponding processing of distortion with camera lens is overlapped.
For unfolded image (360 ° of panoramas, 180 ° of scapes of enjoying a double blessing, 4 frames extract or 8 frames extract), overlapped elements 505 can be weighed It folds time, date/time, camera title and azimuth etc. and exports image.In addition, in order to make observer (operator) energy It identifies direction, the predeterminated position or direction etc. in " entrance " or " hall " can be shown in picture end.
Illustrate the mistake of processing performed by picture pick-up device 101 according to the second embodiment below with reference to the flow chart of Fig. 9 Journey.
In step S901, full side that control unit 508 will project on imaging sensor 502 via fish eye lens 501 Bit image 106 is sent to display equipment 105 to be displayed in full screen.In step S902, control unit 508 controls mobile physical examination Unit 509 is surveyed to detect moving body in omnidirectional images 106.
In step S903, the foot of detected moving body (subject 104) is arranged in control unit 508.Such as reference Described in Fig. 7 and 8, vertical reference position is set by the upright position (centers of omnidirectional images 106) of picture pick-up device 101 201, and set the position nearest with vertical reference position 201 of subject 104 to the position of the foot 802 of subject 104 It sets.
In step S904, control unit 508 controls setting unit 510 so that the foot 802 relative to subject 104 is arranged Position of centre of gravity 701.In step S905, control unit 508 controls detection line setting unit 1001 with setting and position of centre of gravity 701 corresponding detection lines 801.
In step S906, the control of control unit 508 is by detection unit 511, to be based on detection line 801 and subject 104 position of centre of gravity 701 judges whether the position of centre of gravity 701 of subject 104 has passed through detection line 801.Thus judgement is shot Whether body 104 has passed through detection line 203.If subject 104 has passed through detection line 203, processing enters step S907.It is another Aspect, if subject 104 does not pass through detection line 203, processing returns to step S901.
In step s 907, control unit 508 is executed with subject 104 across the corresponding processing of detection line 203.At this The details of reason is identical as in first embodiment, thus the description thereof will be omitted.Reason everywhere shown in Fig. 9 this terminate.
As described above, in the present embodiment, the upright position of comprehensive camera is defined as base position, it is based on benchmark Positional relationship between position and body position shot and foot is set, and be newly arranged subject position of centre of gravity and with center of gravity position Set corresponding detection line.Position of centre of gravity based on subject carries out passing through detection relative to passing through for detection line.Therefore, i.e., Make in subject by passing through near detection line, error detection can also be reduced and realized stable pass through inspection It surveys.
Note that the present embodiment can be combined with first embodiment.Except whether the foot position of subject passes through detection Other than line, it can also judge whether the position of centre of gravity of subject passes through the second detection line.It, can be with when the two conditions all meet It is judged as that subject passes through.
Picture pick-up device 1101 be described below not be vertically downward but by have it is angled in a manner of the example installed.
Figure 11 is the figure for showing the example of configuration of supervision camera system.With reference to Figure 11, picture pick-up device 1101 is to include Fish-eye comprehensive camera, and installed with the inclination angle alpha relative to vertical direction.The composition of picture pick-up device Element is identical as first or second embodiments, thus the description thereof will be omitted.By subject 104 captured by picture pick-up device 1101 Video is sent to client terminal 102 or record server (not shown) via network 103.The video shown on picture pick-up device 105 1106 be the video (omnidirectional images) of picture pick-up device 1101.
Control unit 508 detects inclination angle alpha of the picture pick-up device 1101 relative to vertical direction, and according to tilt angle Vertical reference position is arranged on omnidirectional images 1106 in α.This allows to detect the foot of subject according to tilt angle, and And detection accuracy can be improved.For example, if tilt angle relative to vertical direction is 90 °, circular omnidirectional images 1106 lower part is vertical reference position.
According to the present embodiment, even if erroneous detection can also be reduced by passing through near detection line in subject It surveys and realizes and stable pass through detection.
Other embodiments
The embodiment of the present invention can also be realized by following method, that is, pass through network or various storage mediums The software (program) for executing the function of above-described embodiment is supplied to system or device, the computer of the system or device or in The method that Central Processing Unit (CPU), microprocessing unit (MPU) read and execute program.
While the present invention has been described with reference to the exemplary embodiments, it should be appreciated that, the present invention is not limited to disclosed Exemplary embodiments.The scope of the appended claims meets widest explanation, to include all such modifications, equivalent structure and function Energy.

Claims (6)

1. a kind of picture pick-up device, including：
Subject detection unit, for being shot on the direction perpendicular to horizontal plane from camera unit via being arranged in Shooting image captured by comprehensive pick-up lens detects the region of the subject moved on ground,
It is characterized in that, further including：
Setting unit, for by it is described shooting image in the position phase perpendicular to comprehensive pick-up lens set by ground Corresponding position is set as base position, and the institute in the shooting image is arranged based on the distance away from the base position State the position of the foot of subject；
Determining means, for the position based on the foot, to determine judgement position of the subject in the shooting image It sets；And
By detection unit, for detect the subject whether pass through on ground by detection line, it is described to pass through detection line Based on the pre-set detection line of instruction according to operator,
Wherein, described to judge whether position passes through conduct by what detection unit detected the subject in the shooting image The subject judges that position was set to the respective heights relative to ground passes through detection line.
2. picture pick-up device according to claim 1, wherein the position of the foot is determined as described by the determining means Judge position；And
Described detected by detection unit described judges whether position passes through the detection line on ground.
3. picture pick-up device according to claim 1, wherein the determining means will connect the base position and described On the line of the position of foot and the position of centre of gravity of the subject of the position predetermined distance of the foot is set as the judgement Position；And
The picture pick-up device further includes：
Detection line setting unit, for by by the position of centre of gravity relative to being defined as and the base position and the quilt It takes the photograph in the height reflection detection line on the ground of the position of the corresponding foot of the shortest distance between body, to be arranged the Two detection lines,
Wherein, whether the position of centre of gravity for detecting the subject by detection unit passes through second detection line.
4. picture pick-up device according to claim 1, wherein the determining means is opposite according to the comprehensive pick-up lens In the tilt angle of the vertical direction on real space, the judgement position is set.
5. a kind of supervision camera system, including：
Picture pick-up device according to claim 1；And
Information processing equipment, for obtaining image from the picture pick-up device via network.
6. a kind of control method of picture pick-up device, including：
It is clapped from camera unit via the comprehensive pick-up lens shot on the direction perpendicular to horizontal plane is arranged in The shooting image taken the photograph detects the region of the subject moved on ground,
It is characterized in that, further including：
By being set with the position corresponding perpendicular to comprehensive pick-up lens set by ground in the shooting image It is set to base position, and the foot for shooting the subject in image is set based on the distance away from the base position The position in portion；
Based on the position of the foot, to determine judgement position of the subject in the shooting image；And
Detect the subject whether pass through on ground by detection line, it is described by detection line based on the finger according to operator Show pre-set detection line,
Wherein, that the subject is detected in the shooting image judges whether position passes through the judgement as the subject What position was set to the respective heights relative to ground passes through detection line.
CN201510751841.0A 2014-11-07 2015-11-06 Picture pick-up device and its control method and supervision camera system Active CN105592301B (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2014227491A JP6512793B2 (en) 2014-11-07 2014-11-07 Imaging device, surveillance camera system, control method and program for imaging device
JP2014-227491 2014-11-07

Publications (2)

Publication Number Publication Date
CN105592301A CN105592301A (en) 2016-05-18
CN105592301B true CN105592301B (en) 2018-11-23

Family

ID=54360844

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510751841.0A Active CN105592301B (en) 2014-11-07 2015-11-06 Picture pick-up device and its control method and supervision camera system

Country Status (4)

Country Link
US (1) US10200607B2 (en)
EP (1) EP3018902B1 (en)
JP (1) JP6512793B2 (en)
CN (1) CN105592301B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11252391B2 (en) * 2017-03-06 2022-02-15 Nevermind Capital Llc Methods and apparatus for packing images into a frame and/or including additional content or graphics
TWI624805B (en) * 2017-03-27 2018-05-21 晶睿通訊股份有限公司 Object counting method having route distribution property and related image processing device
JP7063723B2 (en) * 2018-05-22 2022-05-09 本田技研工業株式会社 Display control device and program
CN108762397A (en) * 2018-06-08 2018-11-06 Oppo广东移动通信有限公司 Control method, control assembly, electronic equipment and the storage medium of slide assemblies
US10956782B2 (en) * 2018-11-16 2021-03-23 Qualcomm Incorporated Training for camera lens distortion
CN112468832A (en) * 2020-10-22 2021-03-09 北京拙河科技有限公司 Billion-level pixel panoramic video live broadcast method, device, medium and equipment

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7006950B1 (en) * 2000-06-12 2006-02-28 Siemens Corporate Research, Inc. Statistical modeling and performance characterization of a real-time dual camera surveillance system
JP2011086045A (en) * 2009-10-14 2011-04-28 Giken Torasutemu Kk Assistant/customer separation/aggregation device
CN103179342A (en) * 2011-12-21 2013-06-26 安讯士有限公司 Monitoring camera and method for monitoring
CN103456116A (en) * 2012-05-30 2013-12-18 精工爱普生株式会社 Intrusion detection device, robot system, intrusion detection method, and intrusion detection program

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3218521B2 (en) 1992-09-30 2001-10-15 清水建設株式会社 Moving object detection system using image sensor
JP3183320B2 (en) 1994-08-31 2001-07-09 日本電信電話株式会社 Counting method and apparatus for each moving object direction
JP2002239207A (en) * 2001-02-20 2002-08-27 Omron Corp Card game system, card game apparatus, card for game and game method for card game
US7596241B2 (en) * 2005-06-30 2009-09-29 General Electric Company System and method for automatic person counting and detection of specific events
JP2008016896A (en) * 2006-06-30 2008-01-24 Sony Corp Monitoring apparatus and monitoring method
JP4949106B2 (en) * 2007-03-29 2012-06-06 株式会社リコー Person tracking device, person tracking method and program thereof
US8675090B2 (en) * 2010-12-15 2014-03-18 Panasonic Corporation Image generating apparatus, image generating method, and recording medium
JP6057562B2 (en) * 2012-06-28 2017-01-11 キヤノン株式会社 Information processing apparatus and control method thereof

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7006950B1 (en) * 2000-06-12 2006-02-28 Siemens Corporate Research, Inc. Statistical modeling and performance characterization of a real-time dual camera surveillance system
JP2011086045A (en) * 2009-10-14 2011-04-28 Giken Torasutemu Kk Assistant/customer separation/aggregation device
CN103179342A (en) * 2011-12-21 2013-06-26 安讯士有限公司 Monitoring camera and method for monitoring
CN103456116A (en) * 2012-05-30 2013-12-18 精工爱普生株式会社 Intrusion detection device, robot system, intrusion detection method, and intrusion detection program

Also Published As

Publication number Publication date
US20160134810A1 (en) 2016-05-12
EP3018902B1 (en) 2018-09-19
EP3018902A1 (en) 2016-05-11
CN105592301A (en) 2016-05-18
US10200607B2 (en) 2019-02-05
JP6512793B2 (en) 2019-05-15
JP2016092693A (en) 2016-05-23

Similar Documents

Publication Publication Date Title
CN105592301B (en) Picture pick-up device and its control method and supervision camera system
CN104902246B (en) Video monitoring method and device
CN105611230B (en) Image processing apparatus and image processing method
CN104969538B (en) Manage the mobile augmented reality of closed area
JP5180733B2 (en) Moving object tracking device
CN103179342B (en) CCTV camera and monitoring method
CN106488115B (en) For tracking and sensing the control device and method of the image sensing apparatus of tracking target
CN108737793A (en) Use camera network moving object tracking
WO2014155979A1 (en) Tracking processing device and tracking processing system provided with same, and tracking processing method
CN104966062B (en) Video monitoring method and device
JP5956248B2 (en) Image monitoring device
KR101275297B1 (en) Camera Apparatus of tracking moving object
CN106572298A (en) Display control apparatus and display control method
JP5771039B2 (en) Abandoned person detection device
KR101785017B1 (en) Monitoring camera
JP2013042386A (en) Monitoring system
KR20100025338A (en) System for tracking object using capturing and method thereof
JP2004272756A (en) Device for investigating congestion degree
CN109858319A (en) Image processing equipment and control method and non-transitory computer-readable storage media
JP2010262527A (en) Passing person counting device, passing person counting method and passing person counting program
JP5213883B2 (en) Composite display device
CN107958202A (en) Human body detecting device, the control method of human body detecting device and storage medium
JP2018170575A (en) Monitoring system
JP5546404B2 (en) Surveillance camera, surveillance system, and surveillance method
JP5960471B2 (en) Image monitoring device

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant